Master theses
Deep Neural Network-Based Segmentation of Volumetric Radiological Images
Author
Matyáš Turek
Year
2025
Type
Master thesis
Supervisor
prof. Ing. Vanda Benešová, CSc.
Reviewers
prof. RNDr. Pavel Surynek, Ph.D.
Department
Summary
This thesis deals with lesion segmentation of hypoxic-ischemic encephalopathy in neonatal MRI images using deep neural networks. The work explores and implements various approaches such as super resolution and data synthesis to achieve more accurate segmentation on the BONBID-HIE dataset. As part of this work, we implemented a functional pipeline for creating super resolution 3D MRI images, a pipeline for creating synthetic lesions that were further inpainted into the dataset images, and a segmentation pipeline. The results were discussed and compared.
Computer Vision and Deep Learning Methods for Digital Histopathological Image Processing
Author
Vojtěch Müller
Year
2025
Type
Master thesis
Supervisor
prof. Ing. Vanda Benešová, CSc.
Reviewers
Ing. Daniel Vašata, Ph.D.
Department
Summary
This master's thesis focuses on advanced methods for processing digital histopathological images to improve melanoma cancer prediction using the PUMA dataset. The work focuses on the analysis of current solutions for panoptic segmentation in histopathological data. It proposes a segmentation pipeline in the form of the selected state-of-the-art model TransUnet that is further modified, followed by an Autoencoder for stitching the image patches. This pipeline overcomes the baseline by a 0.06 average DICE score. The thesis includes a detailed description of data preprocessing, hyperparameter optimization, and the implementation of selected models.